An Inequality for Variances of the Discounted Rewards (Q3402070): Difference between revisions

@@ Property / full work available at URL @@
+https://doi.org/10.1239/jap/1261670699
+Normal rank
@@ Property / OpenAlex ID @@
+W2030712766
@@ Property / OpenAlex ID: W2030712766 / rank @@
+Normal rank
@@ Property / cites work @@
+SEMI-MARKOV DECISION PROCESSES
@@ Property / cites work: SEMI-MARKOV DECISION PROCESSES / rank @@
+Normal rank
@@ Property / cites work @@
+Continuous Time Discounted Jump Markov Decision Processes: A Discrete-Event Approach
+Normal rank
@@ Property / cites work @@
+Q5691076
@@ Property / cites work: Q5691076 / rank @@
+Normal rank
@@ Property / cites work @@
+Markov decision processes with a new optimality criterion: Continuous time
+Normal rank
@@ Property / cites work @@
+Q4223074
@@ Property / cites work: Q4223074 / rank @@
+Normal rank
@@ Property / cites work @@
+The variance of discounted Markov decision processes
+Normal rank
@@ Property / cites work @@
+Maximal mean/standard deviation ratio in an undiscounted MDP
+Normal rank
@@ Property / cites work @@
+Mean-Variance Tradeoffs in an Undiscounted MDP
@@ Property / cites work: Mean-Variance Tradeoffs in an Undiscounted MDP / rank @@
+Normal rank
@@ Property / cites work @@
+On the total reward variance for continuous-time Markov reward chains
+Normal rank
@@ Property / cites work @@
+Mean, variance and probabilistic criteria in finite Markov decision processes: A review
+Normal rank